{"id":"W3117059669","doi":"10.18653/v1/2020.coling-main.527","title":"Data Selection for Bilingual Lexicon Induction from Specialized Comparable Corpora","year":2020,"lang":"en","type":"article","venue":"","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université de Montréal; Computer Research Institute of Montréal","funders":"Institut de Valorisation des Données; Agence Nationale de la Recherche","keywords":"Computer science; Artificial intelligence; Exploit; Lexicon; Margin (machine learning); Selection (genetic algorithm); Natural language processing; Machine translation; Computation; Entropy (arrow of time); Machine learning; Algorithm","routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0028775,0.001394361,0.001395308,0.003601321,0.000891828,0.001228229,0.001221011,0.0007420679,0.005991375],"category_scores_gemma":[0.009091569,0.0007397259,0.001353554,0.003936809,0.0007664684,0.002708669,0.003048996,0.001356854,0.005055665],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007219558,"about_ca_system_score_gemma":0.001878145,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00187714,"about_ca_topic_score_gemma":0.004441638,"domain_scores_codex":[0.9976336,0.001080426,0.0002480155,0.0005328348,0.000368216,0.0001369858],"domain_scores_gemma":[0.9964911,0.001751704,0.0001415813,0.0007757579,0.0007303479,0.0001094734],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000705188,0.0003737452,0.003849199,0.0007373007,0.0001579146,0.0004654826,0.0005644517,0.02028563,0.06745207,0.006449685,0.01830346,0.8806558],"study_design_scores_gemma":[0.0005217844,0.0005892245,0.008290646,0.0001400701,0.0002850297,0.0007982976,0.001089524,0.7472425,0.1437553,0.03091298,0.06623002,0.0001446938],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.08159215,0.0006531989,0.8987541,0.0002876451,0.0001398269,0.0005205581,0.003109046,0.01068308,0.004260379],"genre_scores_gemma":[0.3120858,0.000443524,0.64936,0.0002448726,0.0001252861,0.001636291,0.03143996,0.00130839,0.0033558],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.005991375,"threshold_uncertainty_score":0.02004313,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1389098027000213,"score_gpt":0.3420511324608173,"score_spread":0.203141329760796,"validation_status":"score_only:v0-immature-baseline","note":"Baseline scores from an immature model (maturity gate not passed). Scores rank; they never assert a category."}}